Arthrology surgery puncture navigation system based on artificial intelligence

Abstract

The invention relates to the technical field of data processing, in particular to an arthroscopic surgery puncture navigation system based on artificial intelligence, the system comprises an information acquisition module, an information processing module, a puncture area positioning module, a three-dimensional fitting and path planning module and a visualization and interaction module, the information acquisition module is used for acquiring arthroscopic images; the information processing module is used for running an image enhancement strategy, carrying out denoising processing on the arthroscope image and outputting a clear arthroscope image; the puncture area positioning module is used for performing contour extraction on the arthroscope clear image, identifying a key structure in a joint, performing similarity matching on an edge contour and a pre-stored joint anatomical atlas, and positioning a target puncture area; and the three-dimensional fitting and path planning module is used for constructing a dynamic three-dimensional navigation coordinate system in combination with an arthroscope image and planning a puncture needle path on a fitting curved surface.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to an artificial intelligence-based puncture navigation system for joint surgery. Background Art

[0002] Puncture is a key technique in joint surgery, and precise puncture plays a crucial role in surgical success. With the advancement of medical technology, the requirements for surgical precision, safety, and efficiency continue to increase, and traditional surgical puncture methods are no longer able to meet clinical needs. Against this backdrop, AI-based technologies are increasingly being applied in the medical field, providing new solutions for puncture navigation in joint surgery, aiming to improve surgical precision and safety while reducing complications.

[0003] Traditional puncture methods rely heavily on the physician's experience and feel, lacking precise positioning and navigation, which can easily lead to puncture deviations, affecting surgical outcomes and increasing surgical risks. For example, they may accidentally injure surrounding vital tissues and organs, prolonging the operation. Arthroscopic images are susceptible to noise during acquisition, such as impurities within the joint cavity and uneven lighting, resulting in poor image quality. This makes it difficult for physicians to clearly observe the structures within the joint, which in turn affects the accurate judgment of the puncture area. Existing technologies may not be able to dynamically navigate according to changes during the surgical process, making it difficult to adjust the puncture path in a timely manner and unable to adapt to the complex and changing circumstances of the operation.

[0004] Therefore, it is necessary to propose an artificial intelligence-based puncture navigation system for joint surgery. Summary of the Invention

[0005] In view of the shortcomings of the existing technology, the present invention proposes an artificial intelligence-based arthritis surgery puncture navigation system. The information processing module runs the image enhancement strategy to not only extract the RGB channel intensity of each pixel point of the arthroscopic image to construct a noise intensity set, but also collects auxiliary input parameters such as the pressure in the joint cavity, the movement speed of the mirror end, and the ambient light intensity. The convolutional neural network model is used for training and denoising, and a clear arthroscopic image is output, which provides a clear and accurate image basis for subsequent operations and facilitates doctors to observe the intra-articular structure. The puncture area positioning module uses the Canny edge detection algorithm to extract the continuous edges of the clear arthroscopic image, and uses the multi-threshold gradient detection unit to identify the key structures in the joint and calculate the gradient amplitude to determine the edge. The edge contour is then matched with the pre-stored joint anatomical atlas for similarity, which can accurately locate the target puncture area and improve the accuracy of puncture; the three-dimensional fitting and path planning module aligns the target contour in the arthroscopic image with the preoperative model, optimizes the spatial alignment through the ICP algorithm to generate a fused three-dimensional model, and fits the guiding surface equation of the puncture path with the tip of the arthroscope as the origin, realizing the construction of a dynamic three-dimensional navigation coordinate system and the planning of the puncture needle path, which can provide accurate navigation for surgery in real time and adapt to changes during the operation; the visualization and interaction module provides a navigation visualization interface and interactive functions, and triggers an alarm when the puncture deviation exceeds the threshold, which facilitates the doctor to adjust the puncture operation in time and improve the safety and reliability of the operation.

[0006] To achieve the above object, the technical solution of the present invention is as follows:

[0007] An artificial intelligence-based arthritis surgery puncture navigation system is characterized in that the system includes an information acquisition module, an information processing module, a puncture area positioning module, a three-dimensional fitting and path planning module, and a visualization and interaction module, wherein the information acquisition module is used to obtain arthroscopic images; the information processing module is used to run an image enhancement strategy, denoise the arthroscopic images, and output clear arthroscopic images; the puncture area positioning module is used to extract the contours of the clear arthroscopic images, identify key structures in the joints, and match the edge contours with pre-stored joint anatomical atlases for similarity to locate the target puncture area; the three-dimensional fitting and path planning module is used to combine the arthroscopic images, construct a dynamic three-dimensional navigation coordinate system, and plan the puncture needle path on the fitting surface; the visualization and interaction module is used to provide a navigation visualization interface and interactive functions, and trigger an alarm when the puncture deviation exceeds the threshold.

[0008] A further improvement of the present invention is that the information processing module runs an image enhancement strategy, and the image enhancement strategy includes the following specific steps:

[0009] S11, extracting the RGB channel intensity of each pixel in the arthroscopic image and constructing a noise intensity set; at the same time, collecting the pressure in the joint cavity, the movement speed of the end of the mirror, and the ambient light intensity as auxiliary input parameters;

[0010] S12. Construct a convolutional neural network model, wherein the convolutional neural network model takes the arthroscopic image and auxiliary input parameters as input, and the denoised arthroscopic clear image as output, and uses the sum of the squares of the differences between the pixel value of each pixel point of the predicted arthroscopic clear image and the pixel value of each pixel point of the actual arthroscopic clear image as the prediction target. The convolutional neural network model is trained until the sum of the squares of the differences between the pixel value of each pixel point of the predicted arthroscopic clear image and the pixel value of each pixel point of the actual arthroscopic clear image reaches convergence, and the training is stopped; the arthroscopic clear image is output.

[0011] A further improvement of the present invention is that the puncture area positioning module includes a contour extraction unit, a multi-threshold gradient detection unit and a target puncture area positioning unit; the contour extraction unit is used to extract continuous edges of a clear arthroscopic image using a Canny edge detection algorithm; the multi-threshold gradient detection unit is used to identify key structures within the joint and perform gradient amplitude calculations, and use pixel points with gradient amplitudes greater than the gradient threshold as edge contours of key structures within the joint; the target puncture area positioning unit is used to perform similarity matching between the edge contour and a pre-stored joint anatomical atlas to locate the target puncture area.

[0012] A further improvement of the present invention is that the three-dimensional fitting and path planning module includes a three-dimensional model construction unit and a puncture path planning unit; the three-dimensional model construction unit is used to align the target contour in the arthroscopic image with the preoperative model, optimize the spatial alignment through the ICP algorithm, and generate a fused three-dimensional model; the puncture path planning unit is used to fit the guiding surface equation of the puncture path with the tip of the arthroscope as the origin.

[0013] A further improvement of the present invention is that the multi-threshold gradient detection unit is used to identify key structures within the joint and perform gradient amplitude calculation, and the pixel points with gradient amplitude greater than the gradient threshold are used as the edge contour of the key structure within the joint. The specific formula for the gradient amplitude calculation is:

[0014]

[0015] Among them, Δ x I represents the horizontal gradient, Δ y I represents the vertical gradient.

[0016] A further improvement of the present invention is that the puncture path planning unit is used to fit the guiding surface equation of the puncture path with the tip of the arthroscope as the origin; the guiding surface equation of the puncture path fitting includes the following specific contents: constructing the target contour point set {P i (x i ,y i ,z i )}, fitting the guiding surface equation of the puncture path, the guiding surface equation of the puncture path is:

[0017] z=f(x,y)=ax 2 +by 2 +cxy+dx+ey+f;

[0018] The least squares method is used to solve the coefficients a, b, c, d, e, and f and minimize the residual. The formula for minimizing the residual is:

[0019] The technical effects of the present invention are as follows:

[0020] The present invention proposes an artificial intelligence-based puncture navigation system for arthroscopic surgery. The information processing module runs an image enhancement strategy to not only extract the RGB channel intensity of each pixel point in the arthroscopic image to construct a noise intensity set, but also collects auxiliary input parameters such as the pressure in the joint cavity, the movement speed of the mirror end, and the ambient light intensity. The convolutional neural network model is used for training and denoising, and a clear arthroscopic image is output, which provides a clear and accurate image basis for subsequent operations and facilitates doctors to observe the structure inside the joint; the puncture area positioning module uses the Canny edge detection algorithm to extract the continuous edge of the clear arthroscopic image, identifies the key structure in the joint through the multi-threshold gradient detection unit and calculates the gradient amplitude to determine the edge contour, and then By performing similarity matching with the pre-existing joint anatomical atlas, the target puncture area can be accurately located, thereby improving the accuracy of puncture. The three-dimensional fitting and path planning module aligns the target contour in the arthroscopic image with the preoperative model, optimizes the spatial alignment through the ICP algorithm to generate a fused three-dimensional model, and fits the guiding surface equation of the puncture path with the tip of the arthroscope as the origin, thereby realizing the construction of a dynamic three-dimensional navigation coordinate system and the planning of the puncture needle path, and can provide accurate navigation for the surgery in real time and adapt to changes during the operation. The visualization and interaction module provides a navigation visualization interface and interactive functions, and triggers an alarm when the puncture deviation exceeds the threshold, so that the doctor can adjust the puncture operation in time and improve the safety and reliability of the operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Other features, objects and advantages of the present invention will become more apparent upon reading the detailed description of non-limiting embodiments made with reference to the following drawings:

[0022] Figure 1This is a schematic structural diagram of an artificial intelligence-based joint surgery puncture navigation system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0023] Example 1

[0024] This embodiment proposes an artificial intelligence-based puncture navigation system for arthritis surgery. The information processing module runs an image enhancement strategy to not only extract the RGB channel intensity of each pixel in the arthroscopic image to construct a noise intensity set, but also collects auxiliary input parameters such as the pressure in the joint cavity, the movement speed of the mirror end, and the ambient light intensity. It uses a convolutional neural network model for training and denoising, and outputs clear arthroscopic images, providing a clear and accurate image basis for subsequent operations and facilitating doctors to observe the structures within the joint. The puncture area positioning module uses the Canny edge detection algorithm to extract the continuous edges of the clear arthroscopic image, and uses a multi-threshold gradient detection unit to identify key structures within the joint and calculate the gradient amplitude to determine the edge contour. Then, similarity matching is performed with the pre-stored joint anatomical atlas to accurately locate the target puncture area and improve the accuracy of puncture; the three-dimensional fitting and path planning module aligns the target contour in the arthroscopic image with the preoperative model, optimizes the spatial alignment through the ICP algorithm to generate a fused three-dimensional model, and fits the guiding surface equation of the puncture path with the tip of the arthroscope as the origin, realizing the construction of a dynamic three-dimensional navigation coordinate system and the planning of the puncture needle path, which can provide accurate navigation for the surgery in real time and adapt to changes during the operation; the visualization and interaction module provides a navigation visualization interface and interactive functions, and triggers an alarm when the puncture deviation exceeds the threshold, so that the doctor can adjust the puncture operation in time and improve the safety and reliability of the operation.

[0025] like Figure 1 As shown, the artificial intelligence-based arthritis surgery puncture navigation system is characterized in that the system includes an information acquisition module, an information processing module, a puncture area positioning module, a three-dimensional fitting and path planning module and a visualization and interaction module, the information acquisition module is used to obtain arthroscopic images; the information processing module is used to run the image enhancement strategy, denoise the arthroscopic image and output a clear arthroscopic image; the puncture area positioning module is used to extract the contour of the clear arthroscopic image, identify the key structures in the joint, and match the edge contour with the pre-stored joint anatomical atlas for similarity to locate the target puncture area; the three-dimensional fitting and path planning module is used to combine the arthroscopic image, construct a dynamic three-dimensional navigation coordinate system, and plan the puncture needle path on the fitting surface; the visualization and interaction module is used to provide a navigation visualization interface and interactive functions, and trigger an alarm when the puncture deviation exceeds the threshold.

[0026] Example 2

[0027] In this embodiment, the information processing module executes an image enhancement strategy, which includes the following specific steps:

[0028] S11, extracting the RGB channel intensity of each pixel in the arthroscopic image and constructing a noise intensity set; at the same time, collecting the pressure in the joint cavity, the movement speed of the end of the mirror, and the ambient light intensity as auxiliary input parameters;

[0029] S12. Construct a convolutional neural network model, wherein the convolutional neural network model takes the arthroscopic image and auxiliary input parameters as input, and the denoised arthroscopic clear image as output, and uses the sum of the squares of the differences between the pixel value of each pixel point of the predicted arthroscopic clear image and the pixel value of each pixel point of the actual arthroscopic clear image as the prediction target. The convolutional neural network model is trained until the sum of the squares of the differences between the pixel value of each pixel point of the predicted arthroscopic clear image and the pixel value of each pixel point of the actual arthroscopic clear image reaches convergence, and the training is stopped; the arthroscopic clear image is output.

[0030] In this embodiment, the puncture area positioning module includes a contour extraction unit, a multi-threshold gradient detection unit and a target puncture area positioning unit; the contour extraction unit is used to extract continuous edges of a clear arthroscopic image using a Canny edge detection algorithm; the multi-threshold gradient detection unit is used to identify key structures within the joint and perform gradient amplitude calculations, and use pixel points with gradient amplitudes greater than the gradient threshold as edge contours of key structures within the joint; the target puncture area positioning unit is used to perform similarity matching between the edge contour and a pre-stored joint anatomical atlas to locate the target puncture area.

[0031] Example 3

[0032] In this embodiment, the three-dimensional fitting and path planning module includes a three-dimensional model construction unit and a puncture path planning unit; the three-dimensional model construction unit is used to align the target contour in the arthroscopic image with the preoperative model, optimize the spatial alignment through the ICP algorithm, and generate a fused three-dimensional model; the puncture path planning unit is used to fit the guiding surface equation of the puncture path with the tip of the arthroscope as the origin.

[0033] In this embodiment, the multi-threshold gradient detection unit is used to identify key structures within the joint and perform gradient amplitude calculation, and the pixel points with gradient amplitude greater than the gradient threshold are regarded as the edge contour of the key structure within the joint. The specific formula for the gradient amplitude calculation is:

[0034]

[0035] Among them, Δ x I represents the horizontal gradient, Δ y I represents the vertical gradient.

[0036] Example 4

[0037] In this embodiment, the puncture path planning unit is used to fit the guiding surface equation of the puncture path with the tip of the arthroscope as the origin; the guiding surface equation of the puncture path includes the following specific contents: constructing the target contour point set {P i (x i ,y i ,z i )}, fitting the guiding surface equation of the puncture path, the guiding surface equation of the puncture path is:

[0038] z=f(x,y)=ax 2 +by 2 +cxy+dx+ey+f;

[0039] The least squares method is used to solve the coefficients a, b, c, d, e, and f and minimize the residual. The formula for minimizing the residual is:

[0040] It should be noted here that the information processing module, by running the image enhancement strategy, not only extracts the RGB channel intensity of each pixel point of the arthroscopic image to construct a noise intensity set, but also collects auxiliary input parameters such as the pressure in the joint cavity, the movement speed of the mirror end, and the ambient light intensity, and uses the convolutional neural network model for training and denoising to output a clear arthroscopic image, which provides a clear and accurate image basis for subsequent operations and facilitates doctors to observe the intra-articular structure; the puncture area positioning module uses the Canny edge detection algorithm to extract the continuous edge of the clear arthroscopic image, identifies the key structures in the joint through the multi-threshold gradient detection unit and calculates the gradient amplitude to determine the edge contour, and then compares it with the pre-stored joint anatomy The atlas performs similarity matching, which can accurately locate the target puncture area and improve the accuracy of puncture; the three-dimensional fitting and path planning module aligns the target contour in the arthroscopic image with the preoperative model, optimizes the spatial alignment through the ICP algorithm to generate a fused three-dimensional model, and fits the guiding surface equation of the puncture path with the tip of the arthroscope as the origin, realizing the construction of a dynamic three-dimensional navigation coordinate system and the planning of the puncture needle path, which can provide accurate navigation for the surgery in real time and adapt to changes during the operation; the visualization and interaction module provides a navigation visualization interface and interactive functions, and triggers an alarm when the puncture deviation exceeds the threshold, so that the doctor can adjust the puncture operation in time and improve the safety and reliability of the operation.

[0041] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0042] It should be understood that determining B based on A does not mean determining B based solely on A. B can also be determined based on A and / or other information.

[0043] The above embodiments can be implemented in whole or in part through software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. A computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions according to the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired network or / and a wireless network. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains a collection of one or more available media. The available media can be magnetic media (e.g., floppy disks, hard disks, tapes), optical media (e.g., DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0044] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0045] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0046] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only one type. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0047] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0048] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0049] Throughout this specification, references to terms such as "one embodiment," "example," or "specific example" indicate that the specific features, structures, materials, or characteristics described in conjunction with that embodiment or example are included in at least one embodiment or example of the present invention. In this specification, schematic representations of these terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0050] The preferred embodiments of the present invention disclosed above are intended only to help illustrate the present invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the present invention to specific embodiments. Obviously, many modifications and variations are possible based on the contents of this specification. These embodiments are selected and described in detail in this specification to better explain the principles and practical applications of the present invention, thereby enabling those skilled in the art to better understand and utilize the present invention. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. Artificial intelligence-based puncture navigation system for joint surgery, characterized by: The system includes an information acquisition module, an information processing module, a puncture area positioning module, a three-dimensional fitting and path planning module, and a visualization and interaction module. The information acquisition module is used to obtain arthroscopic images; The information processing module is used to run the image enhancement strategy, perform denoising on the arthroscopic image and output a clear arthroscopic image; The puncture area positioning module is used to extract the contour of the clear arthroscopic image, identify the key structures in the joint, and match the edge contour with the pre-stored joint anatomical atlas for similarity to locate the target puncture area; the three-dimensional fitting and path planning module is used to combine the arthroscopic image, construct a dynamic three-dimensional navigation coordinate system, and plan the puncture needle path on the fitting surface; the visualization and interaction module is used to provide a navigation visualization interface and interactive functions, and trigger an alarm when the puncture deviation exceeds the threshold.

2. The artificial intelligence-based joint surgery puncture navigation system according to claim 1, characterized in that: The information processing module executes an image enhancement strategy, which includes the following specific steps: S11, extracting the RGB channel intensity of each pixel in the arthroscopic image and constructing a noise intensity set; at the same time, collecting the pressure in the joint cavity, the movement speed of the end of the mirror, and the ambient light intensity as auxiliary input parameters; S12. Construct a convolutional neural network model, wherein the convolutional neural network model takes the arthroscopic image and auxiliary input parameters as input, and the denoised arthroscopic clear image as output, and uses the sum of the squares of the differences between the pixel value of each pixel point of the predicted arthroscopic clear image and the pixel value of each pixel point of the actual arthroscopic clear image as the prediction target. The convolutional neural network model is trained until the sum of the squares of the differences between the pixel value of each pixel point of the predicted arthroscopic clear image and the pixel value of each pixel point of the actual arthroscopic clear image reaches convergence, and the training is stopped; the arthroscopic clear image is output.

3. The artificial intelligence-based joint surgery puncture navigation system according to claim 2, characterized in that: The puncture area positioning module includes a contour extraction unit, a multi-threshold gradient detection unit and a target puncture area positioning unit; the contour extraction unit is used to extract the continuous edge of the arthroscopic clear image using the Canny edge detection algorithm; The multi-threshold gradient detection unit is used to identify key structures within the joint and calculate the gradient amplitude, and use the pixel points with gradient amplitude greater than the gradient threshold as the edge contour of the key structure within the joint; the target puncture area positioning unit is used to match the edge contour with the pre-stored joint anatomical atlas for similarity to locate the target puncture area.

4. The artificial intelligence-based joint surgery puncture navigation system according to claim 3, characterized in that: The three-dimensional fitting and path planning module includes a three-dimensional model construction unit and a puncture path planning unit; the three-dimensional model construction unit is used to align the target contour in the arthroscopic image with the preoperative model, optimize the spatial alignment through the ICP algorithm, and generate a fused three-dimensional model; the puncture path planning unit is used to fit the guiding surface equation of the puncture path with the tip of the arthroscope as the origin.

5. The artificial intelligence-based joint surgery puncture navigation system according to claim 4 is characterized in that: The multi-threshold gradient detection unit is used to identify the key structures in the joint and perform gradient amplitude calculation, and the pixel points with gradient amplitude greater than the gradient threshold are regarded as the edge contour of the key structure in the joint. The specific formula for the gradient amplitude calculation is: Among them, Δ x I represents the horizontal gradient, Δ y I represents the vertical gradient.

6. The artificial intelligence-based joint surgery puncture navigation system according to claim 5, characterized in that: The puncture path planning unit is used to fit the guiding surface equation of the puncture path with the tip of the arthroscope as the origin; the guiding surface equation of the puncture path fitting includes the following specific contents: constructing the target contour point set {P i (x i ,y i ,z i )}, fitting the guiding surface equation of the puncture path, the guiding surface equation of the puncture path is: z=f(x,y)=ax 2 +by 2 +cxy+dx+ey+f; The least squares method is used to solve the coefficients a, b, c, d, e, and f and minimize the residual. The formula for minimizing the residual is:

Images